Joint Scheduling of eMBB and URLLC Traffic in Space-Air-Ground Integrated Networks

In order to maximize network performance, we use the Deep Reinforcement Learning (DRL) approach in this research to dynamically arrange flexible transmission intervals at the time slot level. By engaging with the environment, resources are dynamically and appropriately assigned to URLLC traffic. Traffic scheduling algorithms taking into account enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low-Latency Communication (URLLC) service demands are carefully built with incentive functions. Real-time decisions are made using DRL approach to overcome uncertainty problems. The resource slicing problem is formulated as an optimization problem to enhance reliability and maximize average data rate of eMBB consumers while respecting URLLC constraints.